Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Abstract. The accuretely counting of airborne urediniospores of Puccinia striiformis f. sp. tritici (Pst) in wheat fields is an important process for devising strategies early and effectively controlling wheat stripe rust. This paper proposed a new segmentation and counting algorithm based on microimgae processiong to quantitative counting of airborne urediospores of Pst. Firstly, microimages of urediniospores were collected using portable volumetric spore traps in an indoor simulation. Then, the urediniospores were automatically segmented and counted using a series of image processing approaches, including image segmentation using the K-means clustering algorithm, image pre-processing, the identification of touching urediniospores based on the shape factor and area, and touching urediniospore contour segmentation based on concavity and contour segment merging. Finally, the all ellipse numbers were added up as the number of urediospores. To verify the effectiveness of the proposed algorithm, that was compared with the watershed transformation method. The experimental results showed that: The lowest counting accuracy of the proposed method was 92.7%, the highest counting accuracy was 100%. The total average counting accuracy was 98.6%, which was an increase of 6 percentage points over that of the watershed transformation algorithm (92.6%). In conclusion, experimental results show that the proposed method is efficient and accurate for the automatic segmentation and counting of trapped urediniospores, which provide technical support for the development of on-line airborne urediospores monitoring equipment.